mlsanityData to 7 Oct 2026

PIXART-δ: Fast and Controllable Image Generation with Latent Consistency Models

arXiv 2401.05252 ↗First posted 10 Jan 2024cs.CVcited by 139

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

This technical report introduces PIXART-δ, a text-to-image synthesis framework that integrates the Latent Consistency Model (LCM) and ControlNet into the advanced PIXART-α model. PIXART-α is recognized for its ability to generate high-quality images of 1024px resolution through a remarkably efficient training process. The integration of LCM in PIXART-δ significantly accelerates the inference speed, enabling the production of high-quality images in just 2-4 steps. Notably, PIXART-δ achieves a breakthrough 0.5 seconds for generating 1024x1024 pixel images, marking a 7x improvement over the PIXART-α. Additionally, PIXART-δ is designed to be efficiently trainable on 32GB V100 GPUs within a single day. With its 8-bit inference capability (von Platen et al., 2023), PIXART-δ can synthesize 1024px images within 8GB GPU memory constraints, greatly enhancing its usability and accessibility. Furthermore, incorporating a ControlNet-like module enables fine-grained control over text-to-image diffusion models. We introduce a novel ControlNet-Transformer architecture, specifically tailored for Transformers, achieving explicit controllability alongside high-quality image generation. As a state-of-the-art, open-source image generation model, PIXART-δ offers a promising alternative to the Stable Diffusion family of models, contributing significantly to text-to-image synthesis.

Key facts. Cited by 139 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 9 of its 12 references that are in the map. First posted on arXiv 10 Jan 2024.

Builds on

9 of 12 references.

Closest ancestors · 8

Same direction, newest first

  1. 2023LCM-LoRA: A Universal Stable-Diffusion Acceleration Module9 Nov
  2. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference6 Oct
  3. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis30 Sep
  4. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis4 Jul
  5. 2023Consistency Models2 Mar
  6. 2023Simple diffusion: End-to-end diffusion for high resolution images26 Jan
  7. 2023On the Importance of Noise Scheduling for Diffusion Models26 Jan
  8. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec

Other references · 1

  1. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 45; 2025: 68; 2026: 26.

139 papers.

Sort:

By area:

  1. 2024OminiControl: Minimal and Universal Control for Diffusion Transformercited by 334
  2. 2024PixArt-Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generationcited by 326
  3. 2024VD3D: Taming Large Video Diffusion Transformers for 3D Camera Controlcited by 156
  4. 2024AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformerscited by 151
  5. 2024CFG++: Manifold-constrained Classifier Free Guidance for Diffusion Modelscited by 138
  6. 2024HART: Efficient Visual Generation with Hybrid Autoregressive Transformercited by 128
  7. 2024FORA: Fast-Forward Caching in Diffusion Transformer Accelerationcited by 127
  8. 2025OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Modelscited by 127
  9. 2024FasterCache: Training-Free Video Diffusion Model Acceleration with High Qualitycited by 115
  10. 2024Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyondcited by 111
  11. 2024Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Modelscited by 107
  12. 2025Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Controlcited by 95
38 more
  1. 2024Dora: Sampling and Benchmarking for 3D Shape Variational Auto-Encoderscited by 93
  2. 2025SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillationcited by 85
  3. 2025Latent Diffusion Model without Variational Autoencodercited by 83
  4. 2025Training-free and Adaptive Sparse Attention for Efficient Long Video Generationcited by 65
  5. 2024Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion Modelcited by 64
  6. 2024FasterDiT: Towards Faster Diffusion Transformers Training without Architecture Modificationcited by 64
  7. 2025TIIF-Bench: How Does Your T2I Model Follow Your Instructions?cited by 64
  8. 2024Dynamic Diffusion Transformercited by 60
  9. 2024ManiCM: Real-time 3D Diffusion Policy via Consistency Model for Robotic Manipulationcited by 57
  10. 2024SwiftBrush v2: Make Your One-step Diffusion Model Better Than Its Teachercited by 45
  11. 2024ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformercited by 45
  12. 2024Vivid-ZOO: Multi-View Video Generation with Diffusion Modelcited by 40
  13. 2024EvalMuse-40K: A Reliable and Fine-Grained Benchmark with Comprehensive Human Annotations for Text-to-Image Generation Model Evaluationcited by 37
  14. 2025Reangle-A-Video: 4D Video Generation as Video-to-Video Translationcited by 35
  15. 2024DrivingSphere: Building a High-fidelity 4D World for Closed-loop Simulationcited by 34
  16. 2024DiVE: DiT-based Video Generation with Enhanced Controlcited by 31
  17. 2025OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulationcited by 30
  18. 2024STAR: Scale-wise Text-conditioned AutoRegressive image generationcited by 28
  19. 2024LoTLIP: Improving Language-Image Pre-training for Long Text Understandingcited by 27
  20. 2025StarGen: A Spatiotemporal Autoregression Framework with Video Diffusion Model for Scalable and Controllable Scene Generationcited by 26
  21. 2024CityCraft: A Real Crafter for 3D City Generationcited by 25
  22. 2024Efficient Diffusion Transformer with Step-wise Dynamic Attention Mediatorscited by 24
  23. 2025BlockDance: Reuse Structurally Similar Spatio-Temporal Features to Accelerate Diffusion Transformerscited by 24
  24. 2025UniForm: A Unified Multi-Task Diffusion Transformer for Audio-Video Generationcited by 21
  25. 2025RelaCtrl: Relevance-Guided Efficient Control for Diffusion Transformerscited by 18
  26. 2025DreamLayer: Simultaneous Multi-Layer Generation via Diffusion Modecited by 17
  27. 2025TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flowscited by 17
  28. 2024Mimir: Improving Video Diffusion Models for Precise Text Understandingcited by 16
  29. 2025Exploring Multimodal Diffusion Transformers for Enhanced Prompt-based Image Editingcited by 16
  30. 2025Group Critical-token Policy Optimization for Autoregressive Image Generationcited by 16
  31. 2025Semantics-Guided Diffusion for Deep Joint Source-Channel Coding in Wireless Image Transmissioncited by 15
  32. 2025SketchVideo: Sketch-based Video Generation and Editingcited by 15
  33. 2026Think-Then-Generate: Reasoning-Aware Text-to-Image Diffusion with LLM Encoderscited by 15
  34. 2024DiC: Rethinking Conv3x3 Designs in Diffusion Modelscited by 14
  35. 2025MeshCraft: Exploring Efficient and Controllable Mesh Generation with Flow-based DiTscited by 14
  36. 2024Editing Music with Melody and Text: Using ControlNet for Diffusion Transformercited by 13
  37. 2025DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizercited by 13
  38. 2024EdgeFusion: On-Device Text-to-Image Generationcited by 12

50 most cited of 139 All 139 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Reward Guided Latent Consistency Distillation
  2. 2026PixSDS: Why Latent SDS Makes Noisy Pixels
  3. 2025Layton: Latent Consistency Tokenizer for 1024-pixel Image Reconstruction and Generation by 256 Tokens
  4. 2024DreamLCM: Towards High-Quality Text-to-3D Generation via Latent Consistency Model
  5. 2024Phased Consistency Models
  6. 2024RL for Consistency Models: Faster Reward Guided Text-to-Image Generation
  7. 2025ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generation
  8. 2023KOALA: Empirical Lessons Toward Memory-Efficient and Fast Diffusion Models for Text-to-Image Synthesis